Predictive Likelihood Ratios for Language Model Watermark Detection
Quick summary
arXiv:2609.15657v1 Announce Type: cross Abstract: Keyed watermark detection tests dependence between observed tokens and pseudorandom variables reconstructed from a secret key. Building on the pivotal framework of Li et al. (2025), we construct predictive likelihood ratios that average over uncertain probability deficits and residual-tail distributions. The aim is robust detection power across alternative specifications without requiring a single signal-strength tuning. A mixture prior combines tail shape and effective width; hierarchical extensions allow within-document variation in deficit o
Key takeaways
- arXiv:2609.15657v1 Announce Type: cross Abstract: Keyed watermark detection tests dependence between observed tokens and pseudorandom variables reconstructed from a secret key.
- Building on the pivotal framework of Li et al.
- (2025), we construct predictive likelihood ratios that average over uncertain probability deficits and residual-tail distributions.
Why it matters
“Predictive Likelihood Ratios for Language Model Watermark Detection” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments